{"id":"https://openalex.org/W4410991889","doi":"https://doi.org/10.1093/bioinformatics/btaf222","title":"NEFFy: a versatile tool for computing the number of effective sequences","display_name":"NEFFy: a versatile tool for computing the number of effective sequences","publication_year":2025,"publication_date":"2025-05-31","ids":{"openalex":"https://openalex.org/W4410991889","doi":"https://doi.org/10.1093/bioinformatics/btaf222","pmid":"https://pubmed.ncbi.nlm.nih.gov/40459855"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaf222","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf222","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf222/63427211/btaf222.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf222/63427211/btaf222.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115040301","display_name":"Maryam Haghani","orcid":"https://orcid.org/0009-0006-3377-0417"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maryam Haghani","raw_affiliation_strings":["Department of Computer Science, Virginia Tech , Blacksburg, VA 24061,","Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States of America"],"raw_orcid":"https://orcid.org/0009-0006-3377-0417","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech , Blacksburg, VA 24061,","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States of America","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018409409","display_name":"Debswapna Bhattacharya","orcid":"https://orcid.org/0000-0002-9630-0141"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debswapna Bhattacharya","raw_affiliation_strings":["Department of Computer Science, Virginia Tech , Blacksburg, VA 24061,","Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States of America"],"raw_orcid":"https://orcid.org/0000-0002-9630-0141","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech , Blacksburg, VA 24061,","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States of America","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073142937","display_name":"T. M. Murali","orcid":"https://orcid.org/0000-0003-3688-4672"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"T M Murali","raw_affiliation_strings":["Department of Computer Science, Virginia Tech , Blacksburg, VA 24061,","Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States of America"],"raw_orcid":"https://orcid.org/0000-0003-3688-4672","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Virginia Tech , Blacksburg, VA 24061,","institution_ids":["https://openalex.org/I859038795"]},{"raw_affiliation_string":"Department of Computer Science, Virginia Tech, Blacksburg, VA 24061, United States of America","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I859038795"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":4.8708,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.95477665,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"42","issue":"6","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.4733000099658966,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.4733000099658966,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.14890000224113464,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.1088000014424324,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.78208327293396},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.7114989757537842},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.689937174320221},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.6526652574539185},{"id":"https://openalex.org/keywords/documentation","display_name":"Documentation","score":0.6360921859741211},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6107707023620605},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5995545387268066},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5794764161109924},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42901724576950073},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.38471394777297974},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37362271547317505},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3244245648384094},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2339160144329071},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.20725375413894653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.15773597359657288},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.126455157995224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.78208327293396},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.7114989757537842},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.689937174320221},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.6526652574539185},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6360921859741211},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6107707023620605},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5995545387268066},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5794764161109924},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42901724576950073},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.38471394777297974},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37362271547317505},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3244245648384094},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2339160144329071},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.20725375413894653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.15773597359657288},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.126455157995224}],"mesh":[{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012313","descriptor_name":"RNA","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaf222","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf222","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf222/63427211/btaf222.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:40459855","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40459855","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:13242184","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13242184/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaf222","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaf222","pdf_url":"https://academic.oup.com/bioinformatics/advance-article-pdf/doi/10.1093/bioinformatics/btaf222/63427211/btaf222.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1596990522","display_name":"PIPP Phase I: Community Informed Computational Prevention of Pandemics","funder_award_id":"2200045","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3891976813","display_name":null,"funder_award_id":"R35GM138146","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G4230058533","display_name":"CAREER: Bringing Models to Native: Open Access Bioinformatics for Protein Structure Refinement","funder_award_id":"2208679","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6249070199","display_name":null,"funder_award_id":"DBI 2208679","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410991889.pdf","grobid_xml":"https://content.openalex.org/works/W4410991889.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2132241624","https://openalex.org/W4311683883","https://openalex.org/W4212902261","https://openalex.org/W4400311305","https://openalex.org/W2790811106","https://openalex.org/W4385413248","https://openalex.org/W2789551765","https://openalex.org/W3097598351","https://openalex.org/W3170192653","https://openalex.org/W4287775886"],"abstract_inverted_index":{"MOTIVATION:":[0],"A":[1],"Multiple":[2],"Sequence":[3],"Alignment":[4],"(MSA)":[5],"contains":[6],"fundamental":[7],"evolutionary":[8],"information":[9],"that":[10],"is":[11,130],"useful":[12],"in":[13,93,144],"the":[14,32,61,68,117,136],"prediction":[15],"of":[16,20,27,34,36,113],"structure":[17],"and":[18,22,55,77,87,99,107,124,146,164],"function":[19],"proteins":[21],"nucleic":[23],"acids.":[24],"The":[25,141],"\"Number":[26],"Effective":[28],"Sequences\"":[29],"(NEFF)":[30],"quantifies":[31],"diversity":[33],"sequences":[35],"an":[37],"MSA.":[38],"While":[39],"several":[40],"tools":[41,51,92],"embed":[42],"NEFF":[43,79,105,109],"calculation":[44,106],"with":[45,116],"various":[46],"options,":[47],"none":[48],"are":[49,150,166],"standalone":[50],"for":[52,84,111],"this":[53],"purpose,":[54],"they":[56],"do":[57],"not":[58],"offer":[59],"all":[60,74],"available":[62,151],"options.":[63],"RESULTS:":[64],"We":[65],"developed":[66],"NEFFy,":[67],"first":[69],"software":[70,134],"package":[71],"to":[72,119,122],"integrate":[73],"these":[75,160],"options":[76],"calculate":[78],"across":[80],"diverse":[81],"MSA":[82],"formats":[83],"proteins,":[85,115],"RNAs,":[86],"DNAs.":[88],"It":[89],"surpasses":[90],"existing":[91],"functionality":[94],"without":[95],"compromising":[96],"computational":[97],"efficiency":[98],"scalability.":[100],"NEFFy":[101,129],"also":[102],"offers":[103],"per-residue":[104],"supports":[108],"computation":[110],"MSAs":[112],"multimeric":[114],"capability":[118],"be":[120],"extended":[121],"DNAs":[123],"RNAs.":[125],"AVAILABILITY":[126],"AND":[127],"IMPLEMENTATION:":[128],"released":[131],"as":[132],"open-source":[133],"under":[135],"GNU":[137],"Public":[138],"License":[139],"v3.0.":[140],"source":[142],"code":[143],"C++":[145],"a":[147],"Python":[148],"wrapper":[149],"at":[152,168],"https://github.com/Maryam-Haghani/NEFFy.":[153],"To":[154],"ensure":[155],"users":[156],"can":[157],"fully":[158],"leverage":[159],"capabilities,":[161],"comprehensive":[162],"documentation":[163],"examples":[165],"provided":[167],"https://Maryam-Haghani.github.io/NEFFy.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":5}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
